Search

As data-driven models gain importance in driving decisions and processes, recently, it has become increasingly important to visualize the data with both speed and accuracy. A massive volume of data is presently generated in the educational sphere from various learning platforms, tools, and institutions. The visual analytics of educational big data has the capability to improve student learning, develop strategies for personalized learning, and improve faculty productivity. However, there are limited advancements in the education domain for data-driven decision making leveraging the recent advancements in the field of machine learning. Some of the recent tools such as Tableau, Power BI, Microsoft Azure suite, Sisense, etc., leverage artificial intelligence and machine learning techniques to visualize data and generate insights from them; however, their applicability in educational advances is limited. This paper focuses on leveraging machine learning and visualization techniques to demonstrate their utility through a practical implementation using K-12 state assessment data compiled from the institutional websites of the States of Texas and Louisiana. Effective modeling and predictive analytics are the focus of the sample use case presented in this research. Our approach demonstrates the applicability of web technology in conjunction with machine learning to provide a cost-effective and timely solution to visualize and analyze big educational data. Additionally, ad hoc visualization provides contextual analysis in areas of concern for education agencies (EAs). [ABSTRACT FROM AUTHOR]

There is a concerted effort to build intelligent sea and numerous artificial intelligence technologies have been explored. At present, more and more people are engaged in the research of deep reinforcement learning algorithm, and its mainstream application is in the field of games. Reinforcement learning has conquered chess belonging to complete information game, and Texas poker belonging to incomplete information games. And it reached or even surpassed the highest player level of mankind in E-sports games with huge state space and complex action space. However, reinforcement learning algorithm still has great challenges in fields such as automatic driving. The main reason is that the training of reinforcement learning needs to build an environment for interacting with agents. However, it is very difficult to construct realistic simulation scenes, and there is no guarantee that we will not encounter the state that the agent has not seen. Therefore, it is necessary to explore the simulation scene first. Based on this, this paper mainly studies reinforcement learning in simulation scenario. There are huge challenges in migrating them to real scenario applications, especially in sea missions. Aiming at the heterogeneous multi-agent game confrontation scenario, this paper proposes a sea battlefield game confrontation decision algorithm based on multi-agent deep deterministic policy gradient. The algorithm combines long short-term memory and actor-critic, which not only realizes the convergence of the algorithm in huge state space and action space, but also solves the problem of sparse real rewards. At the same time, imitation learning is integrated into the decision algorithm, which not only improves the convergence speed of the algorithm, but also greatly improves the effectiveness of the algorithm. The results show that the algorithm can deal with a variety of different tactical sea battlefield scenarios, make flexible decisions according to the changes of the enemy, and the average winning rate is close to 90%. [ABSTRACT FROM AUTHOR]

Rural and urban America have becoming increasingly divided, both politically and economically. Entrepreneurship can help rural communities catch back up by jumpstarting economic growth, creating jobs, and building resilience to economic shocks. However, less is known about firm creation in rural areas compared to urban areas. To that end, in this paper we ask: What factors predict firm creation in rural America? Our analysis, based on a comparative framework involving multiple machine learning modeling techniques, helps addresses three gaps in academic literature on rural firm creation. First, entrepreneurship research stretches across disciplines, often using econometric methods to identify the effect of a specific variable, rather than comparing the predictive importance of multiple variables. Second, research on firm creation centers on high-tech, urban firms. Third, modern machine learning techniques have not yet been applied in an integrated way to address rural entrepreneurship, a complex economic and policy problem that defies simple, monocausal claims. In this paper, we apply four machine learning methods (subset selection, lasso, random forest, and extreme gradient boosting) to a novel dataset to examine what social and economic factors are predictive of firm growth in rural Texas counties from 2008–2018. Our results suggest that some factors commonly discussed as promoting entrepreneurship (e.g., access to broadband and patents) may not be as predictive as socioeconomic ones (age distribution, ethnic diversity, social capital, and immigration). We also find that the strength of specific industries (oil, wind, healthcare, and elder/childcare) predicts firm growth, as does the number of local banks. Most factors predictive of firm growth in rural counties are distinct from those in urban counties, supporting the argument that rural entrepreneurship is a distinct phenomenon worthy of distinct focus. More broadly, this multi-model approach can offer initial, focusing guidance to policymakers seeking to address similarly complex policy problems. [ABSTRACT FROM AUTHOR]

The COVID-19 (SARS-CoV-2 virus) pandemic has led to a substantial loss of human life worldwide by providing an unparalleled challenge to the public health system. The economic, psychological, and social disarray generated by the COVID-19 pandemic is devastating. Public health experts and epidemiologists worldwide are struggling to formulate policies on how to control this pandemic as there is no effective vaccine or treatment available which provide long-term immunity against different variants of COVID-19 and to eradicate this virus completely. As the new cases and fatalities are recorded daily or weekly, the responses are likely to be repeated or longitudinally correlated. Thus, studying the impact of available covariates and new cases on deaths from COVID-19 repeatedly would provide significant insights into this pandemic's dynamics. For a better understanding of the dynamics of spread, in this paper, we study the impact of various risk factors on the new cases and deaths over time. To do that, we propose a marginal-conditional based joint modelling approach to predict trajectories, which is crucial to the health policy planners for taking necessary measures. The conditional model is a natural choice to study the underlying property of dependence in consecutive new cases and deaths. Using this model, one can examine the relationship between outcomes and predictors, and it is possible to calculate risks of the sequence of events repeatedly. The advantage of repeated measures is that one can see how individual responses change over time. The predictive accuracy of the proposed model is also compared with various machine learning techniques. The machine learning algorithms used in this paper are extended to accommodate repeated responses. The performance of the proposed model is illustrated using COVID-19 data collected from the Texas Health and Human Services. [ABSTRACT FROM AUTHOR]

Tree crown width relates directly to wood quality and tree growth. The traditional method used to measure crown width is labor-intensive and time-consuming. Pairing imagery taken by an unmanned aerial vehicle (UAV) with a deep learning algorithm such as a faster region-based convolutional neural network (Faster-RCNN) has the potential to be an alternative to the traditional method. In this study, Faster-RCNN outperformed single-shot multibox detector (SSD) for crown detection in a young loblolly pine stand but performed poorly in a dense, mature loblolly pine stand. This paper proposes a novel Faster-RCNN algorithm for tree crown identification and crown width extraction in a forest stand environment with high-density loblolly pine forests. The new algorithm uses Residual Network 101 (ResNet101) and a feature pyramid network (FPN) to build an FPN_ResNet101 structure, improving the capability to model shallow location feature extraction. The algorithm was applied to images from a mature loblolly pine plot in eastern Texas, USA. The results show that the accuracy of crown recognition and crown width measurement using the FPN_ResNet101 structure as the backbone network in Faster-RCNN (FPN_Faster-RCNN_ResNet101) was high, being 95.26% and 0.95, respectively, which was 4.90% and 0.27 higher than when using Faster-RCNN with ResNet101 as the backbone network (Faster-RCNN_ResNet101). The results fully confirm the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Imperfect information games describe many practical applications found in the real world as the information space is rarely fully available. This particular set of problems is challenging due to the random factor that makes even adaptive methods fail to correctly model the problem and find the best solution. Neural Fictitious Self Play (NFSP) is a powerful algorithm for learning approximate Nash equilibrium of imperfect information games from self-play. However, it uses only crude data as input and its most successful experiment was on the in-limit version of Texas Hold’em Poker. In this paper, we develop a new variant of NFSP that combines the established fictitious self-play with neural gradient play in an attempt to improve the performance on large-scale zero-sum imperfect information games and to solve the more complex no-limit version of Texas Hold’em Poker using powerful handcrafted metrics and heuristics alongside crude, raw data. When applied to no-limit Hold’em Poker, the agents trained through self-play outperformed the ones that used fictitious play with a normal-form single-step approach to the game. Moreover, we showed that our algorithm converges close to a Nash equilibrium within the limited training process of our agents with very limited hardware. Finally, our best self-play-based agent learnt a strategy that rivals expert human level. [ABSTRACT FROM AUTHOR]

Approximately one-third of the veteran population suffers from post-traumatic stress disorder, a mental illness that is often co-morbid with social anxiety disorder. Student veterans are especially vulnerable as they struggle to adapt to a new, less structured lifestyle with few peers who understand their difficulties. To support mental health experts in the treatment of social anxiety disorder, this study utilized machine learning to detect anxiety in text transcribed from interviews with patients and applied topic modeling to highlight common stress factors for student veterans. We approach our anxiety detection task by exploring both deep learning and traditional machine learning strategies such as transformers, transfer learning, and support vector classifiers. Our models provide a tool to support psychologists and social workers in treating social anxiety. The results detailed in this paper could also have broader impacts in fields such as pedagogy and public health.1 [ABSTRACT FROM AUTHOR]

This paper presents a novel Lasso Logistic Regression model based on feature-based time series data to determine disease severity and when to administer drugs or escalate intervention procedures in patients with coronavirus disease 2019 (COVID-19). Advanced features were extracted from highly enriched and time series vital sign data of hospitalized COVID-19 patients, including oxygen saturation readings, and with a combination of patient demographic and comorbidity information, as inputs into the dynamic feature-based classification model. Such dynamic combinations brought deep insights to guide clinical decision-making of complex COVID-19 cases, including prognosis prediction, timing of drug administration, admission to intensive care units, and application of intervention procedures like ventilation and intubation. The COVID-19 patient classification model was developed utilizing 900 hospitalized COVID-19 patients in a leading multi-hospital system in Texas, United States. By providing mortality prediction based on time-series physiologic data, demographics, and clinical records of individual COVID-19 patients, the dynamic feature-based classification model can be used to improve efficacy of the COVID-19 patient treatment, prioritize medical resources, and reduce casualties. The uniqueness of our model is that it is based on just the first 24 hours of vital sign data such that clinical interventions can be decided early and applied effectively. Such a strategy could be extended to prioritize resource allocations and drug treatment for futurepandemic events. [ABSTRACT FROM AUTHOR]

Machine learning (ML) is being used regularly in many different fields. This paper compares traditional econometric methods that have better explanations of data analysis to ML methods, focusing on predicting, understanding and unpacking ML methods which have higher prediction accuracies of four key transport‐planning variables: household vehicle‐miles traveled (continuous variable), household vehicle ownership (count variable), mode choice (categorical variable), and land use change (categorical variable with strong spatial interactions). Here, the results of ten ML methods are compared to methods of ordinary least squares (OLS), multinomial logit (MNL), negative binomial and spatial auto‐regressive (SAR). The U.S.'s 2017 National Household Travel Survey and land use data sets from the Dallas‐Ft. Worth region of Texas are used. Results suggest traditional econometric methods work pretty well on the more continuous responses (VMT and vehicle ownership), but the random forest (RF), gradient boosting decision trees (GBDT), and extreme gradient boosting (XGBoost) methods delivered the best results, though the RF model required 30 to almost 60 times more computing time than XGBoost and GBDT methods. The RF, GBDT, XGBoost, light gradient boosting method (lightGBM), and catboost offer better results than other methods for the two "classification" cases, with lightGBM being the most time‐efficient. Importantly, ML methods captured the plateauing effect modelers may expect when extrapolating covariate effects. [ABSTRACT FROM AUTHOR]

Bridge deterioration is inevitable in service, and the inspection and maintenance of bridges are needed to ensure structural integrity. To make cost-effective inspection plans, bridge management departments need degradation models to predict future condition ratings of bridges. Although there have been studies on bridge degradation, the input features of models are selected mostly based on engineering experience, and no effective method has been proposed. Meanwhile, most models based on machine learning (ML) and deep learning (DL) only predict the degradation of bridges in a single year and cannot cover a complete inspection cycle (usually 2 years), providing limited decision support for the transportation departments. Besides, more accurate models are needed to predict the degradation trend of bridges. In response to these problems, an improved ReliefF algorithm is proposed to select features of bridges in the paper. Meanwhile, a new degradation model combining recurrent neural network (RNN) and convolutional neural network (CNN) is established. Historical data of bridges in the US state of Texas from 1992 to 2019 are employed to verify the proposed methods. The result shows that the improved ReliefF algorithm selects the appropriate feature set as the input of the prediction model, and the model accurately predicts the future condition ratings of bridges in the next 3–4 years. The research is beneficial to infrastructure management departments in allocating bridge inspection and maintenance resources reasonably. [ABSTRACT FROM AUTHOR]

Blockchain technology, with its peer-to-peer trading feature, influences the management of energy consumption by offering the potential to transform transparency, efficiency, and sustainability within the energy sector. Nonetheless, there is a need to develop analytical decision-making models tailored for managing peer-to-peer energy transactions to improve energy resilience. Therefore, the purpose of this paper is to address the research question: How can energy distribution systems be protected via blockchain technology to enhance energy resilience and mitigate vulnerabilities to disruptions ? This paper employs a conceptual research model design and a mathematical decision-making model to address the research question by capturing the peer-to-peer trading capability of blockchain technology. The theory of planned behavior provides theoretical explanations for the proposed model. The sample includes longitudinal energy consumption data from 2015 to 2023 in Texas. The findings indicate a significant improvement in energy efficiency along with a considerable decrease in total electricity consumption. Post hoc analysis results reveal that the seasonal autoregressive integrated moving average algorithm is effective as a reliable input for the proposed mathematical model. The significant implications are to implement blockchain-based smart grids in which energy systems become more resilient to disruptions, as the peer-to-peer capability enables users to trade energy. The proposed model suggests that energy will be used more efficiently and effectively. This paper contributes to prior works by introducing a mathematical model that captures the trading behavior of energy consumers. Moreover, this paper proposes the SARIMA algorithm to predict energy demand. • A mathematical peer-to-peer trading model is presented to improve resilience. • A blockchain-based smart grid is presented for consumer energy consumption. • Five machine learning algorithms are presented in energy demand management. • Longitudinal energy consumption data of Texas is used in the model. • Theoretical support is provided using the theory of planned behavior. [ABSTRACT FROM AUTHOR]

Background: This paper studies the temporal consistency of health care expenditures in a large state Medicaid program. Predictive machine learning models were used to forecast the expenditures, especially for the high-cost, high-need (HCHN) patients., Results: We systematically tests temporal correlation of patient-level health care expenditures in both the short and long terms. The results suggest that medical expenditures are significantly correlated over multiple periods. Our work demonstrates a prevalent and strong temporal correlation and shows promise for predicting future health care expenditures using machine learning. Temporal correlation is stronger in HCHN patients and their expenditures can be better predicted. Including more past periods is beneficial for better predictive performance., Conclusions: This study shows that there is significant temporal correlation in health care expenditures. Machine learning models can help to accurately forecast the expenditures. These results could advance the field toward precise preventive care to lower overall health care costs and deliver care more efficiently.

Mental health professionals have relied primarily on clinical evaluations to identify in vivo pathology. As a result, mental health is largely reactive rather than proactive. In an effort to proactively assessmood, we collected continuous neurophysiologic data for ambulatory individuals 8-10 h a day at 1 Hz for 3 weeks (N=24). Data were obtained using a commercial neuroscience platform (Immersion Neuroscience) that quantifies the neural value of social-emotional experiences. These data were related to self-reported mood and energy to assess their predictive accuracy. Statistical analyses quantified neurophysiologic troughs by the length and depth of social-emotional events with low values and neurophysiologic peaks as the complement. Participants in the study had an average of 2.25 (SD = 3.70, Min = 0, Max = 25) neurophysiologic troughs per day and 3.28 (SD = 3.97, Min = 0, Max = 25) peaks. The number of troughs and peaks predicted daily mood with 90% accuracy using least squares regressions and machine learning models. The analysis also showed that women were more prone to low mood compared to men. Our approach demonstrates that a simple count variable derived from a commercially-available platform is a viable way to assess low mood and low energy in populations vulnerable to mood disorders. In addition, peak Immersion events, which are mood-enhancing, may be an effective measure of thriving in adults. [ABSTRACT FROM AUTHOR]

• A two-stage method is proposed for electricity price forecasting. • The method diversifies the data resources improve the forecasting accuracy. • The method is tested using the real-world data of Texas electricity market. • Causal relationship combined with physical models guarantee better results. • Deep neural networks show a great performance in electricity price forecasting. Over the years, the growing penetration of renewable energy into the electricity market has resulted in a significant change in the electricity market price. This change makes the existing forecasting method prone to error, decreasing the economic benefits. Hence, more precise forecasting methods need to be developed. This paper starts with a survey and benchmark of existing machine learning approaches for forecasting the real-time market (RTM) price. While these methods provide sufficient modeling capability via supervised learning, their accuracy is still limited due to the single data source, e.g., historical price information only. In this paper, a novel two-stage supervised learning approach is proposed by diversifying the data sources such as highly correlated power data. This idea is inspired by the recent load forecasting methods that have shown extremely well performances. Specifically, the proposed two-stage method, namely the rerouted method, learns two types of mapping rules. The first one is the mapping between the historical wind power and the historical price. The second is the forecasting rule for wind generation. Based on the two rules, we forecast the price via the forecasted generation and the first learned mapping between power and price. Additionally, we observed that it is not the more training data the better, leading to our validation steps to quantify the best training intervals for different datasets. We conduct comparisons of numerical results between existing methods and the proposed methods based on datasets from the Electric Reliability Council of Texas (ERCOT). For each machine learning step, we examine different learning methods, such as polynomial regression, support vector regression, neural network, and deep neural network. The results show that the proposed method is significantly better than existing approaches when renewables are involved. [ABSTRACT FROM AUTHOR]

This article focuses on developing models that estimate suspended sediment concentrations (SSCs) for the Lower Brazos River, Texas, U.S. Historical samples of SSCs from gauge stations and satellite imagery from Landsat Missions and Sentinel Mission 2 were utilized to develop models to estimate SSCs for the Lower Brazos River. The models used in this study to accomplish this goal include support vector machines (SVMs), artificial neural networks (ANNs), extreme learning machines (ELMs), and exponential relationships. In addition, flow measurements were used to develop rating curves to estimate SSCs for the Brazos River as a baseline comparison of the models that used satellite imagery to estimate SSCs. The models were evaluated using a Taylor Diagram analysis on the test data set developed for the Brazos River data. Fifteen of the models developed using satellite imagery as inputs performed with a coefficient of determination R2 above 0.69, with the three best performing models having an R2 of 0.83 to 0.85. One of the best performing models was then utilized to estimate the SSCs before, during, and after Hurricane Harvey to evaluate the impact of this storm on the sediment dynamics along the Lower Brazos River and the model's ability to estimate SSCs. [ABSTRACT FROM AUTHOR]

Effective habitat management for rare and endangered species requires a thorough understanding of their specific habitat requirements. Although machine learning models have been increasingly used in the analyses of habitat use by wildlife, the primary focus of these models has been on generating spatial predictions. In this study, we used machine learning models in combination with simulated management actions to guide planning and inform managers. We used data from 61 whooping cranes (Grus americana) tagged with GPS telemetry collars between 2009 and 2018 near Aransas National Wildlife Refuge in coastal Texas. We included variables based on topography, land use classification, vegetation height, plant phenology, drought, storm surge events, and both wild and prescribed fires. We then built models at multiple scales: population level, home range level, and roosting and daytime within home range level. We simulated responses to the two primary management actions used to enhance whooping crane habitat on Aransas National Wildlife Refuge: prescribed fire and removal of woody vegetation. At the population and home range scales, land use classification variables had the highest importance values, whereas the combined elevation and bathymetry layer was the most important predictor at both roosting and daytime within home range scales. Our findings revealed that the effects of fire, although generally modest, varied spatially. Areas dominated by estuarine wetlands exhibited higher predicted use within the first months after a fire, whereas those dominated by palustrine wetlands were more likely to be avoided in the immediate postfire years. Our simulation of vegetation removal identified the areas on Aransas National Wildlife Refuge where whooping cranes were predicted to benefit the most if vegetation were removed. These techniques can be used by other researchers wanting to examine and predict the effects of potential management actions on target species habitat. [ABSTRACT FROM AUTHOR]

Inland waters pose a unique challenge for water quality monitoring by remote sensing techniques due to their complicated spectral features and small-scale variability. At the same time, collecting the reference data needed to calibrate remote sensing data products is both time consuming and expensive. In this study, we present the further development of a robotic team composed of an uncrewed surface vessel (USV) providing in situ reference measurements and an unmanned aerial vehicle (UAV) equipped with a hyperspectral imager. Together, this team is able to address the limitations of existing approaches by enabling the simultaneous collection of hyperspectral imagery with precisely collocated in situ data. We showcase the capabilities of this team using data collected in a northern Texas pond across three days in 2020. Machine learning models for 13 variables are trained using the dataset of paired in situ measurements and coincident reflectance spectra. These models successfully estimate physical variables including temperature, conductivity, pH, and turbidity as well as the concentrations of blue–green algae, colored dissolved organic matter (CDOM), chlorophyll-a, crude oil, optical brighteners, and the ions Ca 2 + , Cl − , and Na + . We extend the training procedure to utilize conformal prediction to estimate 90% confidence intervals for the output of each trained model. Maps generated by applying the models to the collected images reveal small-scale spatial variability within the pond. This study highlights the value of combining real-time, in situ measurements together with hyperspectral imaging for the rapid characterization of water composition. [ABSTRACT FROM AUTHOR]

Accurate estimation of reference evapotranspiration (ETr) is important for irrigation planning, water resource management, and preserving agricultural and forest habitats. The widely used Penman–Monteith equation (ASCE-PM) estimates ETr across various timescales using ground weather station data. However, discrepancies persist between estimated ETr and measured ETr obtained from weighing lysimeters (ETr-lys), particularly in advective environments. This study assessed different machine learning (ML) models in comparison to ASCE-PM for ETr estimation in highly advective conditions. Various variable combinations, representing both radiation and aerodynamic components, were organized for evaluation. Eleven datasets (DT) were created for the daily timescale, while seven were established for hourly and quarter-hourly timescales. ML models were optimized by a genetic algorithm (GA) and included support vector regression (GA-SVR), random forest (GA-RF), artificial neural networks (GA-ANN), and extreme learning machines (GA-ELM). Meteorological data and direct measurements of well-watered alfalfa grown under reference ET conditions obtained from weighing lysimeters and a nearby weather station in Bushland, Texas (1996–1998), were used for training and testing. Model performance was assessed using metrics such as root mean square error (RMSE), mean absolute error (MAE), mean bias error (MBE), and coefficient of determination (R2). ASCE-PM consistently underestimated alfalfa ET across all timescales (above 7.5 mm/day, 0.6 mm/h, and 0.2 mm/h daily, hourly, and quarter-hourly, respectively). On hourly and quarter-hourly timescales, datasets predominantly composed of radiation components or a blend of radiation and aerodynamic components demonstrated superior performance. Conversely, datasets primarily composed of aerodynamic components exhibited enhanced performance on a daily timescale. Overall, GA-ELM outperformed the other models and was thus recommended for ETr estimation at all timescales. The findings emphasize the significance of ML models in accurately estimating ETr across varying temporal resolutions, crucial for effective water management, water resources, and agricultural planning. [ABSTRACT FROM AUTHOR]

Average images are often estimated within a sample or theory-derived variables (e.g., conservatives vs. liberals) to understand how social categories are mentally represented. However, average representations can mask large internal heterogeneity, thereby missing unexpected or complex representational clustering. We propose an inverted data-driven approach that first clusters representations by similarity, then identifies variables that differentiate clusters. We apply this approach to characterize mental representations of illegalized immigrants. Representations were collected in Texas and California (N = 1002) using face-based reverse correlation along with variables theorized to influence perceptions of immigrants: attitudes, demographics, ideologies, geography, and a label manipulation (i.e., "undocumented" vs. "illegal" immigrant). Sample- and variable-aggregated images hid representational clusters that differed on visualized facial phenotype and affective expressions. Clustered representations ranged from highly shared to smaller clusters differentiated by demography and social geography: age and local population size perceptions. Data-driven approaches can help reveal meaningful variation in visual representations. [ABSTRACT FROM AUTHOR]

Waterflooding is a widely used secondary oil recovery technique. The oil and gas industry uses a complex reservoir numerical simulation and reservoir engineering analysis to forecast production curves from waterflooding projects. The application of such standard methods at the stage of assessing the potential of a huge number of projects could be computationally inefficient and requires a lot of effort. This paper demonstrates the applicability of machine learning to rate the outcome of waterflooding applied to an oil reservoir. We also explore the relationship of project evaluations by operators at the final stages with several performance metrics for forecasting. Real data about several thousand waterflooding projects in Texas are used in the current study. We compare the ML models rankings of the waterflooding efficiency and the expert rankings. Linear regression models along with neural networks and gradient boosting on decision threes are considered. We show that machine learning models allow reducing computational complexity and can be useful for rating the reservoirs, with respect to the effectiveness of waterflooding. [ABSTRACT FROM AUTHOR]

Data from Landsat-8 and Sentinel-2A/2B are often combined for terrestrial monitoring because of their similar spectral bands. The bidirectional reflectance distribution function (BRDF) effect has been observed in both Landsat-8 and Sentinel-2A/2B reflectance data. However, there is currently no definition of solar zenith angle ( θ s z ) that is suitable for the normalization of the BRDF-adjusted reflectance from the three sensors' combined data. This paper describes the use of four machine learning (ML) models to predict a global θ s z that is suitable for the normalization of bidirectional reflectance from the combined data in 2018. The observed θ s z collected globally, and the three locations in the Democratic Republic of Congo (26.622°E, 0.356°N), Texas in the USA (99.406°W 30.751°N), and Finland (25.194°E, 61.653°N), are chosen to compare the performance of the ML models. At a global scale, the ML models of Support Vector Regression (SVR), Multi-Layer Perception (MLP), and Gaussian Process Regression (GPR) exhibit comparably good performance to that of polynomial regression, considering center latitude as the input to predict the global θ s z . GPR achieves the best overall performance considering the center latitude and acquisition time as inputs, with a root mean square error (RMSE) of 1.390°, a mean absolute error (MAE) of 0.689°, and a coefficient of determination ( R 2 ) of 0.994. SVR shows an RMSE of 1.396°, an MAE of 0.638°, and an R 2 of 0.994, following GPR. For a specific location, the SVR and GPR models have higher accuracy than the polynomial regression, with GPR exhibiting the best performance, when center latitude and acquisition time are considered as inputs. GPR is recommended for predicting the global θ s z using the three sensors' combined data. [ABSTRACT FROM AUTHOR]

The online estimation of battery state of health (SOH) is crucial to ensure the reliability of the energy supply in electric and hybrid vehicles. An approach for enhancing the generalization of SOH estimation using a parallel layer extreme learning machine (PL-ELM) algorithm is analyzed in this paper. The deterministic and stable PL-ELM model is designed to overcome the drift problem that is associated with some conventional machine learning algorithms; hence, extending the application of a single SOH estimation model over a large set of batteries of the same type. The PL-ELM model was trained with selected features that characterize the SOH. These features are acquired as the discrete variation of indicator variables including voltage, state of charge (SOC), and energy releasable by the battery. The model training was performed with an experimental battery dataset collected at room temperature under a constant current load condition at discharge phases. Model validation was performed with a dataset of other batteries of the same type that were aged under a constant load condition. An optimum performance with low error variance was obtained from the model result. The root mean square error (RMSE) of the validated model varies from 0.064% to 0.473%, and the mean absolute error (MAE) error from 0.034% to 0.355% for the battery sets tested. On the basis of performance, the model was compared with a deterministic extreme learning machine (ELM) and an incremental capacity analysis (ICA)-based scheme from the literature. The algorithm was tested on a Texas F28379D microcontroller unit (MCU) board with an average execution speed of 93 μs in real time, and 0.9305% CPU occupation. These results suggest that the model is suitable for online applications. [ABSTRACT FROM AUTHOR]

This paper studies the advantages and disadvantages of different machine learning techniques in predicting ground-motion intensity measures given source characteristics, source-to-site distance, and local site conditions. Typically, linear regression-based models with predefined equations and coefficients are used in ground motion prediction. However, restrictions of the linear regression models may limit their capabilities in extracting complex nonlinear behaviors in the data. Therefore, the present paper comparatively investigates potential benefits from employing other machine learning techniques as statistical method in ground motion prediction such as Artificial Neural Network, Random Forest, and Support Vector Machine. This study quantifies event-to-event and site-to-site variability of the ground motions by implementing them as random effect terms to reduce the aleatory uncertainty. All the algorithms are trained using a selected database of 4528 ground-motions, including 376 seismic events with magnitude 3 to 5.8, recorded over the hypocentral distance range of 4–500 km in Oklahoma, Kansas, and Texas since 2005. The results indicate the algorithms satisfy some physically sound characteristics such as magnitude scaling distance dependency without requiring predefined equations or coefficients. Moreover, it is found that, when sufficient data is available, all the alternative algorithms tend to provide more accurate estimates compared to the conventional linear regression-based method, and particularly, Random Forest outperforms the other algorithms. However, the conventional method is a better tool when limited data is available. • ML-based framework is proposed to develop data-driven GMMs. • ML algorithms are adjusted to consider random effect parameters in GMMs. • ML-based GMMs provide higher accuracy than conventional methods of GMMs. • Physically sound features are observed in ML techniques. [ABSTRACT FROM AUTHOR]

The naturally fractured reservoirs are one of the most challenging due to the tectonic movements that are caused to increase the permeability and conductivity of the fractures. The instability of the permeability and conductivity effects on the fluid flow path causes problems during the transfer of the fluids from the matrix to the fractures and fluid losses during production. In addition, these complications made it difficult for engineers to estimate fluid flow during production. The fracture properties' study is important to model the fluid flow paths such as the fracture porosity, permeability, and the shape factor, which are considered essential in the stability of fluid flow. To examine this, this research introduced new models including decision tree (DT), random forest (RF), K-nearest regression (KNR), ridge regression (RR), and LASSO regression model,. The research studied the fracture properties in naturally fractured reservoirs like the fracture porosity (FP) and the shape factor (SF). The datasets used in this study were collected from previous studies "i.e., Texas oil and gas fields" to build an intelligence-based predictive model for fluid flow characteristics. The prediction process was conducted based on interporosity flow coefficient, storativity ratio, wellbore radius, matrix permeability, and fracture permeability as input data. This study revealed a positive finding for the adopted machine learning (ML) models and was superior in using statistical accuracy metrics. Overall, the research emphasized the implementation of computer-aided models for naturally fractured reservoir analysis, giving more details on the extensive execution techniques, such as injection or the creation of artificial cracks, to minimize hydrocarbon losses or leakage. [ABSTRACT FROM AUTHOR]

The sources of predictability for the February 2021 cold air outbreak (CAO) over the central United States, which led to power grid failures and water delivery shortages in Texas, are diagnosed using a machine learning–based prediction model called a linear inverse model (LIM). The flexibility and low computational cost of the LIM allows its forecasts to be used for identifying and assessing the predictability of key physical processes. The LIM may also be run as a climate model for sensitivity and risk analysis for the same reasons. The February 2021 CAO was a subseasonal forecast of opportunity, as the LIM confidently predicted the CAO's onset and duration four weeks in advance, up to two weeks earlier than other initialized numerical forecast models. The LIM shows that the February 2021 CAO was principally caused by unpredictable internal atmospheric variability and predictable La Niña teleconnections, with nominally predictable contributions from the previous month's sudden stratospheric warming and the Madden–Julian oscillation. When run as a climate model, the LIM estimates that the February 2021 CAO was in the top 1% of CAO severity and suggests that similarly extreme CAOs could be expected to occur approximately every 20–30 years. [ABSTRACT FROM AUTHOR]

Rangeland fine fuel biomass is a key factor in determining fire spread and intensity, while the accuracy of biomass estimation is limited due to inherent heterogeneity in rangeland ecosystems. In this study, high spatial resolution (0.23 m) images were used to classify fuel types and predict rangeland fine fuel biomass in west Texas based on the random forest algorithm. Two biomass models, including one with the fuel type, original spectral bands, and vegetation indices as explanatory variables, and the other that contained a combination of the fuel type, original spectral bands, vegetation, and texture indices as explanatory variables, were assessed. Furthermore, the biomass models were also examined by upscaling the remote sensing images from high to medium (30 m) spatial resolution with the spectral curves derived from Landsat images. The fuel type map had an accuracy of more than 95%, and herbaceous fuel types were kept for estimating fine fuel biomass. The results showed that around 76% and 80% of biomass variances were explained by models without texture indices and with texture indices, respectively. The fuel type and the normalized difference vegetation index (NDVI) were two significant input variables influencing fine fuel biomass for both models and adding texture indices contributed to the improvement of model accuracy. An upscaling analysis for biomass estimation using medium spatial resolution imagery showed that approximately 60% of the variance in biomass was explained by the model. The addition of fractional vegetation cover improved the model performance by explaining an additional 5% of the variance in biomass estimation. These findings indicate that high spatial resolution images have the potential to effectively estimate rangeland fuel types and fine fuel biomass, which can be helpful for mapping the spatial distribution of fine fuels to aid in monitoring and fire management on rangelands. [ABSTRACT FROM AUTHOR]

Globally, native semiarid grasslands and savannas have experienced a densification of woody plant species—leading to a multitude of environmental, economic, and cultural changes. These encroached areas are unique in that the diversity of tree species is small, but at the same time the individual species possess diverse phenological responses. The overall goal of this study was to evaluate the ability of very high resolution drone imagery to accurately map species of woody plants encroaching on semiarid grasslands. For a site in the Edwards Plateau ecoregion of central Texas, we used affordable, very high resolution drone imagery to which we applied maximum likelihood (ML), support vector machine (SVM), random forest (RF), and VGG-19 convolutional neural network (CNN) algorithms in combination with pixel-based (with and without post-processing) and object-based (small and large) classification methods. Based on test sample data (n = 1000) the VGG-19 CNN model achieved the highest overall accuracy (96.9%). SVM came in second with an average classification accuracy of 91.2% across all methods, followed by RF (89.7%) and ML (86.8%). Overall, our findings show that RGB drone sensors are indeed capable of providing highly accurate classifications of woody plant species in semiarid landscapes—comparable to and even greater in some regards to those achieved by aerial and drone imagery using hyperspectral sensors in more diverse landscapes. [ABSTRACT FROM AUTHOR]

• A novel Light Gradient Boosting Machine approach is introduced to model crash counts. • SHAP method is used to quantify the safety effects of key factors. • The effects on different types of crashes are modeled separately and compared. • Modeling crashes by type provides important insights for developing mitigation strategies. • ML and SHAP are useful for developing crash modification factors. Understanding and quantifying the effects of risk factors on crash frequency is of great importance for developing cost-effective safety countermeasures. In this paper, the effects of key crash contributing factors on total crashes and crashes of different collision types are analyzed separately and compared. A novel Machine Learning (ML) method, Light Gradient Boosting Machine (LightGBM), is introduced to model a Texas dataset consisting of vehicle crashes occurred from 2015 to 2017. Compared with other commonly used ML methods such as eXtreme Gradient Boosting (XGBoost), LightGBM performs significantly better in terms of mean absolute error (MAE) and root mean squared error (RMSE). In addition, the SHapley Additive explanation (SHAP) approach is employed to interpret the LightGBM outputs. Significant risk factors are identified, including speed limits, area type, number of lanes, roadway functional class, shoulder width and shoulder type. With the SHAP method, the importance, total effects, and main and interaction effects of risk factors are quantified. The results suggest that the importance of risk factors vary across collision types. Speed limit is a more important risk factor than right/left shoulder width, lane width, and median width for Rear-End (RE) crashes, while the opposite relationship is found for Run-Off-Road (ROR) crashes. Also, it is found that narrow lanes (8ft to 11ft) increase the risk for all types of crashes (i.e., Total , ROR , and RE) in this study. For road segments with 5 or 6 lanes in both directions combined, a lane width greater than or equal to 12ft may help reduce the risk of all types of crashes. These results have important implications for developing accurate crash modification factors and cost-effective safety countermeasures. [ABSTRACT FROM AUTHOR]

To investigate the effect of infrastructure traits on resilience after an exploration, a blast case (West Fertilizer Plant in West, Texas, 2013) was studied, in which all the buildings' damage data (damage pictures, damage scales, and building locations) and resilience information (recovery decision, recovery time, and recovery cost) were collected by authors through site visits, interviews, and appraisal data collections. The novel analysis methods and machine learning algorithms (logistical/linear regression, neural networks, k-nearest neighbor, support vector machine, and gradient boosting) were applied to analyze the West Fertilizer Plant explosion resilience. This study is unique because it implements a resilience analysis for an explosion hazard, although there are some reports discussing the resilience after natural hazards, such as earthquakes, tsunamis, hurricanes, and tornados. Additionally, using machine learning for resilience analysis is also unique. The results can assist decision-makers, civil engineers, and building designers in designing the most resilient structures and/or materials for buildings. The findings in this study can help to develop the most resilient buildings, communities, and cities by considering the impact of explosion hazards. [ABSTRACT FROM AUTHOR]

• Interpretable machine learning is as accurate as deep learning for structured data. • Explainable machine learning unveils the underlying physical processes. • Sequential transfer-learning technique effectively imputes continuous missing data. Due to their enhanced predictive capabilities, noninterpretable machine learning (ML) models (e.g. deep learning) have recently gained a growing interest in analyzing and modeling earth & planetary science data. However, noninterpretable ML models are often treated as "black boxes" by end-users, which could limit their applicability in critical decision making processes. In this paper, we compared the predictive capabilities of three interpretable ML models with three noninterpretable ML models to answer the overarching question: Is it essential to use noninterpretable ML models for enhanced model predictions from hydro-climatological datasets? The ML model development and comparative analysis were performed using measured climate data and synthetic reference crop evapotranspiration ( ET o ) data, with varying levels of missing values, from five weather stations across the karstic Edwards aquifer region in semi-arid south-central Texas. Our analysis revealed that interpretable tree-based ensemble models produce comparable results to noninterpretable deep learning models on structured hydro-climatological datasets. We showed that the tree-based ensemble model is also capable of imputing varying levels of missing climate data at the weather stations, employing the newly developed sequential transfer-learning technique. We applied an explainable machine learning (eXML) framework to quantify the global order of importance of hydro-climatic (predictor) variables on ET o , while highlighting the local dependencies and interactions amongst the predictors and ET o . The eXML framework also revealed the inflection points of the climate variables at which the transition from low to high daily ET o rates occur. The ancillary explainability of ML models are expected to increase users' confidence and support any future decision-making process in water resource management. [ABSTRACT FROM AUTHOR]

• Neighborhoods differ by housing size, shape, orientation, setback, and uniformity. • Manufactured home communities and formal and informal subdivisions differ markedly. • Designated "colonias" and other informal subdivisions have similar morphologies. • Manufactured home communities and manufactured home parks differ by tenure. • Building footprint metrics can correctly classify neighborhoods with 91 % accuracy. Informal subdivisions and manufactured home communities make up a substantial share of the United States' housing stock but receive relatively little attention in the scholarly literature. The time-intensive nature of identifying these often-invisible communities through the analysis of satellite imagery and property records limits their systematic study. What research does exist on these communities suggests that they are often exposed to concentrated forms of economic, social, and environmental vulnerability. This paper uses big data to develop building footprint-derived landscape metrics capable of identifying and distinguishing between informal subdivisions and manufactured home communities based on their morphology. We use a data set of building footprints developed by Microsoft and released publicly in 2018 to measure the size, type, orientation, placement, and uniformity of housing in more than 2000 residential neighborhoods Hidalgo County, Texas, where more than 1000 informal subdivisions have been documented by prior research. Support vector machines (SVMs) and cross-validation are used to test the ability of these metrics to distinguish between three neighborhood types: informal subdivisions, manufactured housing communities, and formal subdivisions (or traditionally planned neighborhoods). Our models can accurately classify these three types of community approximately 91 % of the time. We then examine whether there is evidence to support the further disaggregation of these types of neighborhood, as is the case in both policy and scholarship. Our analysis of the morphology of these communities points to little evidence for the current distinction in state and federal law between pre- and post-1990 informal subdivisions; we do, however, find evidence for the need to distinguish between manufactured home communities with distinct tenure arrangements: namely, land-lease communities that we call manufactured home parks and land-owner communities that we call manufactured home subdivisions. We conclude by offering new research directions made possible by this novel identification method. [ABSTRACT FROM AUTHOR]

Traditionally, structured or coded data fields from a crash report are the basis for identifying crashes involving different types of vehicles, such as farm equipment. However, using only the structured data can lead to misclassification of vehicle or crash type. The objective of the current article is to examine the use of machine learning methods for identifying agricultural crashes based on the crash narrative and to transfer the application of models to different settings (e.g., future years of data, other states). Different data representations (e.g., bag-of-words [BoW], bag-of-keywords [BoK]) and document classification algorithms (e.g., support vector machine [SVM], multinomial naïve Bayes classifier [MNB]) were explored using Texas and Louisiana crash narratives across different time periods. The BoK-support vector classifier (SVC), BoK-MNB, and BoW-SVC models trained with Texas data were better predictive models than the baseline rule-based algorithm on the future year test data, with F1 scores of 0.88, 0.89, 0.85 vs. 0.84. The BoK-MNB trained with Louisiana data performed the closest to the baseline rule-based algorithm on the future year test data (F1 scores, 0.91 baseline rule-based algorithm vs. 0.89 BoK-MNB). The BoK-SVC and BoK-MNB models trained with Texas and Louisiana data were better productive models for Texas future year test data with F1 scores 0.89 and 0.90 vs. 0.84. The BoK-MNB model trained with both states' data was a better predictive model for the Louisiana future year test data, F1 score 0.94 vs. 0.91. The findings of this study support that machine learning methodologies can potentially reduce the amount of human power required to develop key word lists and manually review narratives. [ABSTRACT FROM AUTHOR]

Accurately estimating total organic carbon (TOC) from suites of well logs is essential as it is too costly and time consuming to take direct measurements from core samples in many wells. Unfortunately, the several methods developed over recent decades, based on various correlations and correlation-based machine learning methods, do not provide universally reliable, accurate or easily auditable TOC predictions. A method is developed and its viability evaluated exploiting a promising correlation-free, data-matching routine. This is applied to published well-log curves, with supporting mineralogical data and measured TOC, for two wells penetrating the Lower Barnett Shale formation at distinct settings within the Fort Worth Basin (Texas, U.S.). The method combines between 5 and 10 well log features and evaluates, on a supervised learning basis, multiple cases for nine distinct models at data- record-sampling densities ranging from one record for every 0.5 ft to one record for every 0.04 ft. At zoomed-in sampling densities the model achieves TOC prediction accuracies for the models combining data from both wells of (RMSE ≤ 0.3% and R2 ≥ 0.955) for models involving 6 and 10 input variables. It is the models involving six input variables that have the potential to be applied in unsupervised circumstances to predict TOC in surrounding wells lacking measured TOC, but that potential requires confirmation in future multi-well studies. [ABSTRACT FROM AUTHOR]

Crashes among young and inexperienced drives are a major safety problem in the United States, especially in an area with large rural road networks, such as West Texas. Rural roads present many unique safety concerns that are not fully explored. This study presents a complete machine leaning pipeline to find the patterns of crashes involved with teen drivers no older than 20 on rural roads in West Texas, identify factors that affect injury levels, and build four machine learning predictive models on crash severity. The analysis indicates that the major causes of teen driver crashes in West Texas are teen drivers who failed to control speed or travel at an unsafe speed when they merged from rural roads to highways or approached intersections. They also failed to yield on the undivided roads with four or more lanes, leading to serious injuries. Road class, speed limit, and the first harmful event are the top three factors affecting crash severity. The predictive machine learning model, based on Label Encoder and XGBoost, seems the best option when considering both accuracy and computational cost. The results of this work should be useful to improve rural teen driver traffic safety in West Texas and other rural areas with similar issues. [ABSTRACT FROM AUTHOR]

Texas is the only state that does not mandate that employers carry workers' compensation (WC) insurance coverage. In place of traditional WC, companies can choose to offer alternative "non-subscription" disability plans to workers. Little large-scale empirical research has studied the consequences of switching from traditional WC to non-subscription plans. We use a difference-in-differences estimator along with a novel machine learning approach to compare effects of switching to non-subscription plans for employees in Texas versus contemporaneously measured non-Texas-based employees for 25 large companies. Our results indicate that total medical payments dropped by roughly 40% from switching to non-subscription plans, consisting of reductions in hospital spending, physician spending, and other medical spending. Similarly, indemnity payments dropped by 70% and number of reported lost days dropped by 80%. Accumulating all sources of spending, we find that total expense associated with workplace injury fell by approximately 46% after switching to the non-subscription program. [ABSTRACT FROM AUTHOR]

The identification of critical periods and business cycles contributes significantly to the analysis of financial markets and the macroeconomy. Financialization and cointegration place a premium on the accurate recognition of time-varying volatility in commodity markets, especially those for crude oil and refined fuels. This article seeks to identify critical periods in the trading of energy-related commodities as a step toward understanding the temporal dynamics of those markets. This article proposes a novel application of unsupervised machine learning. A suite of clustering methods, applied to conditional volatility forecasts by trading days and individual assets or asset classes, can identify critical periods in energy-related commodity markets. Unsupervised machine learning achieves this task without rules-based or subjective definitions of crises. Five clustering methods—affinity propagation, mean-shift, spectral, k-means, and hierarchical agglomerative clustering—can identify anomalous periods in commodities trading. These methods identified the financial crisis of 2008–2009 and the initial stages of the COVID-19 pandemic. Applied to four energy-related markets—Brent, West Texas intermediate, gasoil, and gasoline—the same methods identified additional periods connected to events such as the September 11 terrorist attacks and the 2003 Persian Gulf war. t-distributed stochastic neighbor embedding facilitates the visualization of trading regimes. Temporal clustering of conditional volatility forecasts reveals unusual financial properties that distinguish the trading of energy-related commodities during critical periods from trading during normal periods and from trade in other commodities in all periods. Whereas critical periods for all commodities appear to coincide with broader disruptions in demand for energy, critical periods unique to crude oil and refined fuels appear to arise from acute disruptions in supply. Extensions of these methods include the definition of bull and bear markets and the identification of recessions and recoveries in the real economy. [ABSTRACT FROM AUTHOR]